Quantification of Uncertainty Associated with Evidence Layers in Mineral Prospectivity Mapping Using Direct Sampling and Convolutional Neural Network

Mineral prospectivity mapping (MPM) mainly focuses on searching prospective areas for a particular type of mineral deposits. However, MPM is typically subject to uncertainties originated from conceptual mineral deposit models, geoscience data, and prediction models. This study utilizes a hybrid model combining a direct sampling algorithm and a convolutional neural network to quantify the uncertainty associated with the evidence layers in MPM. Specifically, a direct sampling algorithm was first used to simulate equiprobable evidence layers that followed the similar pattern of geological features. A convolutional neural network was then employed to produce mineral prospectivity maps by integrating the simulated evidence layers. The initial risk–return analysis was conducted based on the obtained mineral prospectivity maps to search for areas linked to high potential and low risk. Finally, a Markowitz mean–variance model was adopted to further outline prior prospective areas to support future mineral exploration in the high-potential areas. A case study of mapping mineral prospectivity for gold polymetallic deposits in the Middle–Lower Yangtze River Valley metallogenic belt in the southeastern Hubei Province of China was implemented. The comparative results indicated that the hybrid model of the direct sampling algorithm and convolutional neural network, which considered the uncertainty of evidence layers, achieved a higher success rate and prediction accuracy than the deterministic framework.